AGENT SKILL

example-web-search

Example HTTP tool definition for a fictional web search API. Copy and adapt for real services.

License 许可
MIT
最近更新
2026-04-30
Stars
★ 1
Forks
2

01 前言 Front Matter

name
example-web-search
metadata
{ "harness-tags": "tool,example,web-search", "harness-author": "human", "harness-status": "draft", "harness-related": "research", "harness-script-source": "auto-generated-from-tools" }
description
Example HTTP tool definition for a fictional web search API. Copy and adapt for real services.

02 资源文件 2

03 SKILL.md 正文

Tool: Example Web Search (template)

This is a template tool definition. Its status is example, so validators and loaders will recognize it as non-executable scaffolding. Copy this file to tools/<your-tool>.md, change the status to active, and point it at a real service.

Authentication

Set the API key in your environment:

export WEB_SEARCH_API_KEY="your-key-here"

The tool reads WEB_SEARCH_API_KEY at call time. Never hardcode keys in this file.

Operations

search

Method: GET URL: https://api.example.com/v1/search Headers: Authorization: Bearer $WEB_SEARCH_API_KEY

Query parameters:

  • q (string, required) — search query
  • limit (integer, optional, default 10) — max results, 1-50
  • lang (string, optional, default "en") — ISO 639-1 code

Response: JSON with results: [{title, url, snippet}]

Example call

curl -H "Authorization: Bearer $WEB_SEARCH_API_KEY" \
  "https://api.example.com/v1/search?q=climate+change&limit=5"

Notes

  • Rate limit: 100 requests / minute (fictional).
  • This endpoint does not exist. Swap it for a real provider (Brave, Tavily, Serper, etc.) before marking the tool active.

Related: [research]

Available scripts

  • scripts/call.sh — Auto-generated from this tool's Operations section. Review before relying on it.

04 同仓库更多 Skills

Phoenixrr2113
Phoenixrr2113/agent-harness

research

Conduct research.

资料检索与研究
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

{{NAME=null}=null}

Briefly describe what this skill does AND when to use it. Use imperative phrasing ("Use this skill when..."). Aim for 80-500 chars. Include keywords the model can pattern-match against the user's prompt.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

working-in-a-git-repo

Operating manual for dev work: worktree discipline, build/test/lint commands, file ownership zones, commit style, and a verification checklist before reporting done. Use when starting any feature/fix work in this repo.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

test-runner

Runs the project's test suite (or a targeted subset), parses the output, and reports pass/fail with failing-test details. Use when you need to know test status; call with the test command to run, or leave blank for the project default.

测试与质量Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

reviewer

Reviews a diff or change set for bugs, security issues, test gaps, and style. Use when evaluating a code change, reviewing a pull request, or running a structured review pass before merge.

Skill与智能体开发
★ 1
Phoenixrr2113
Phoenixrr2113/agent-harness

fix-failing-tests

Seven-step flow for diagnosing and fixing failing tests. Use when the user asks to fix failing tests, green the suite, or says 'tests are red' — works through reproduce → read → root-cause → propose → apply → verify → commit.

测试与质量
★ 1